!pip install seaborn 

WARNING: You are using pip version 21.0.1; however, version 21.3.1 is available.
You should consider upgrading via the 'c:\users\2104944461\anaconda3\python.exe -m pip install --upgrade pip' command.

Looking in indexes: https://pypi.org/simple, http://nexus.viavarejo.com.br/repository/pypi-data-science/simple, http://nexus.viavarejo.com.br/repository/pypi-data-science/pypi
Requirement already satisfied: seaborn in c:\users\2104944461\anaconda3\lib\site-packages (0.11.0)
Requirement already satisfied: scipy>=1.0 in c:\users\2104944461\anaconda3\lib\site-packages (from seaborn) (1.6.1)
Requirement already satisfied: numpy>=1.15 in c:\users\2104944461\anaconda3\lib\site-packages (from seaborn) (1.19.5)
Requirement already satisfied: matplotlib>=2.2 in c:\users\2104944461\anaconda3\lib\site-packages (from seaborn) (3.3.2)
Requirement already satisfied: pandas>=0.23 in c:\users\2104944461\anaconda3\lib\site-packages (from seaborn) (1.1.3)
Requirement already satisfied: python-dateutil>=2.1 in c:\users\2104944461\anaconda3\lib\site-packages (from matplotlib>=2.2->seaborn) (2.8.1)
Requirement already satisfied: cycler>=0.10 in c:\users\2104944461\anaconda3\lib\site-packages (from matplotlib>=2.2->seaborn) (0.10.0)
Requirement already satisfied: certifi>=2020.06.20 in c:\users\2104944461\anaconda3\lib\site-packages (from matplotlib>=2.2->seaborn) (2020.12.5)
Requirement already satisfied: pillow>=6.2.0 in c:\users\2104944461\anaconda3\lib\site-packages (from matplotlib>=2.2->seaborn) (8.0.1)
Requirement already satisfied: kiwisolver>=1.0.1 in c:\users\2104944461\anaconda3\lib\site-packages (from matplotlib>=2.2->seaborn) (1.3.0)
Requirement already satisfied: pyparsing!=2.0.4,!=2.1.2,!=2.1.6,>=2.0.3 in c:\users\2104944461\anaconda3\lib\site-packages (from matplotlib>=2.2->seaborn) (2.4.7)
Requirement already satisfied: six in c:\users\2104944461\anaconda3\lib\site-packages (from cycler>=0.10->matplotlib>=2.2->seaborn) (1.15.0)
Requirement already satisfied: pytz>=2017.2 in c:\users\2104944461\anaconda3\lib\site-packages (from pandas>=0.23->seaborn) (2020.1)

Analise Preparação de Dados

Dataset: CSGO Winner

Nome do arquivo: csgo_round_snapshots.xlsx

o Fonte: https://www.kaggle.com/christianlillelund/csgo-round-winner-classification

o Contexto: este dataset contém o resultado de 122 mil momentos que aconteceram durante mais de 700 partidas de campeonatos de alto nível do jogo Counter-Strike: Global Offensive. Temos dados como, por exemplo, o arsenal de ambas as equipes (CT e T), o dinheiro disponível para as duas equipes, o mapa, entre outros. A ideia é prever o vencedor da partida (round_winner).

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
%matplotlib inline

base = pd.read_csv("csgo_round_snapshots.csv")

import seaborn as sns 
sns.set_theme(style="white")

Mapa de Calor - Valores Nan

sns.heatmap(base.isnull().T)

<AxesSubplot:>

Total de Linhas na Base

base['round_winner'].count()

122410

Limpar e Normalizar os dados

base.groupby(['map']).count()

	time_left	ct_score	t_score	ct_health	t_health	ct_money	t_money	ct_helmets	t_helmets	ct_defuse_kits	ct_players_alive	t_players_alive	ct_weapon_ak47	t_weapon_ak47	ct_weapon_aug	t_weapon_aug	ct_weapon_awp	t_weapon_awp	ct_weapon_bizon	t_weapon_bizon	ct_weapon_cz75auto	t_weapon_cz75auto	ct_weapon_elite	t_weapon_elite	ct_weapon_famas	t_weapon_famas	ct_weapon_g3sg1	t_weapon_g3sg1	ct_weapon_galilar	t_weapon_galilar	ct_weapon_glock	t_weapon_glock	ct_weapon_m249	t_weapon_m249	ct_weapon_m4a1s	t_weapon_m4a1s	ct_weapon_m4a4	t_weapon_m4a4	ct_weapon_mac10	t_weapon_mac10	ct_weapon_mag7	t_weapon_mag7	ct_weapon_mp5sd	t_weapon_mp5sd	ct_weapon_mp7	t_weapon_mp7	ct_weapon_mp9	t_weapon_mp9	ct_weapon_negev	t_weapon_negev	ct_weapon_nova	t_weapon_nova	ct_weapon_p90	t_weapon_p90	ct_weapon_r8revolver	t_weapon_r8revolver	ct_weapon_sawedoff	t_weapon_sawedoff	ct_weapon_scar20	t_weapon_scar20	ct_weapon_sg553	t_weapon_sg553	ct_weapon_ssg08	t_weapon_ssg08	ct_weapon_ump45	t_weapon_ump45	ct_weapon_xm1014	t_weapon_xm1014	ct_weapon_deagle	t_weapon_deagle	ct_weapon_fiveseven	t_weapon_fiveseven	ct_weapon_usps	t_weapon_usps	ct_weapon_p250	t_weapon_p250	ct_weapon_p2000	t_weapon_p2000	ct_weapon_tec9	t_weapon_tec9	ct_grenade_hegrenade	t_grenade_hegrenade	ct_grenade_flashbang	t_grenade_flashbang	ct_grenade_smokegrenade	t_grenade_smokegrenade	ct_grenade_incendiarygrenade	t_grenade_incendiarygrenade	ct_grenade_molotovgrenade	t_grenade_molotovgrenade	ct_grenade_decoygrenade	t_grenade_decoygrenade	round_winner
map
de_cache	145	145	145	145	145	145	145	145	145	145	145	145	145	145	145	145	145	145	145	145	145	145	145	145	145	145	145	145	145	145	145	145	145	145	145	145	145	145	145	145	145	145	145	145	145	145	145	145	145	145	145	145	145	145	145	145	145	145	145	145	145	145	145	145	145	145	145	145	145	145	145	145	145	145	145	145	145	145	145	145	145	145	145	145	145	145	145	145	145	145	145	145	145
de_dust2	22144	22144	22144	22144	22144	22144	22144	22144	22144	22144	22144	22144	22144	22144	22144	22144	22144	22144	22144	22144	22144	22144	22144	22144	22144	22144	22144	22144	22144	22144	22144	22144	22144	22144	22144	22144	22144	22144	22144	22144	22144	22144	22144	22144	22144	22144	22144	22144	22144	22144	22144	22144	22144	22144	22144	22144	22144	22144	22144	22144	22144	22144	22144	22144	22144	22144	22144	22144	22144	22144	22144	22144	22144	22144	22144	22144	22144	22144	22144	22144	22144	22144	22144	22144	22144	22144	22144	22144	22144	22144	22144	22144	22144
de_inferno	23811	23811	23811	23811	23811	23811	23811	23811	23811	23811	23811	23811	23811	23811	23811	23811	23811	23811	23811	23811	23811	23811	23811	23811	23811	23811	23811	23811	23811	23811	23811	23811	23811	23811	23811	23811	23811	23811	23811	23811	23811	23811	23811	23811	23811	23811	23811	23811	23811	23811	23811	23811	23811	23811	23811	23811	23811	23811	23811	23811	23811	23811	23811	23811	23811	23811	23811	23811	23811	23811	23811	23811	23811	23811	23811	23811	23811	23811	23811	23811	23811	23811	23811	23811	23811	23811	23811	23811	23811	23811	23811	23811	23811
de_mirage	18576	18576	18576	18576	18576	18576	18576	18576	18576	18576	18576	18576	18576	18576	18576	18576	18576	18576	18576	18576	18576	18576	18576	18576	18576	18576	18576	18576	18576	18576	18576	18576	18576	18576	18576	18576	18576	18576	18576	18576	18576	18576	18576	18576	18576	18576	18576	18576	18576	18576	18576	18576	18576	18576	18576	18576	18576	18576	18576	18576	18576	18576	18576	18576	18576	18576	18576	18576	18576	18576	18576	18576	18576	18576	18576	18576	18576	18576	18576	18576	18576	18576	18576	18576	18576	18576	18576	18576	18576	18576	18576	18576	18576
de_nuke	19025	19025	19025	19025	19025	19025	19025	19025	19025	19025	19025	19025	19025	19025	19025	19025	19025	19025	19025	19025	19025	19025	19025	19025	19025	19025	19025	19025	19025	19025	19025	19025	19025	19025	19025	19025	19025	19025	19025	19025	19025	19025	19025	19025	19025	19025	19025	19025	19025	19025	19025	19025	19025	19025	19025	19025	19025	19025	19025	19025	19025	19025	19025	19025	19025	19025	19025	19025	19025	19025	19025	19025	19025	19025	19025	19025	19025	19025	19025	19025	19025	19025	19025	19025	19025	19025	19025	19025	19025	19025	19025	19025	19025
de_overpass	14081	14081	14081	14081	14081	14081	14081	14081	14081	14081	14081	14081	14081	14081	14081	14081	14081	14081	14081	14081	14081	14081	14081	14081	14081	14081	14081	14081	14081	14081	14081	14081	14081	14081	14081	14081	14081	14081	14081	14081	14081	14081	14081	14081	14081	14081	14081	14081	14081	14081	14081	14081	14081	14081	14081	14081	14081	14081	14081	14081	14081	14081	14081	14081	14081	14081	14081	14081	14081	14081	14081	14081	14081	14081	14081	14081	14081	14081	14081	14081	14081	14081	14081	14081	14081	14081	14081	14081	14081	14081	14081	14081	14081
de_train	13491	13491	13491	13491	13491	13491	13491	13491	13491	13491	13491	13491	13491	13491	13491	13491	13491	13491	13491	13491	13491	13491	13491	13491	13491	13491	13491	13491	13491	13491	13491	13491	13491	13491	13491	13491	13491	13491	13491	13491	13491	13491	13491	13491	13491	13491	13491	13491	13491	13491	13491	13491	13491	13491	13491	13491	13491	13491	13491	13491	13491	13491	13491	13491	13491	13491	13491	13491	13491	13491	13491	13491	13491	13491	13491	13491	13491	13491	13491	13491	13491	13491	13491	13491	13491	13491	13491	13491	13491	13491	13491	13491	13491
de_vertigo	11137	11137	11137	11137	11137	11137	11137	11137	11137	11137	11137	11137	11137	11137	11137	11137	11137	11137	11137	11137	11137	11137	11137	11137	11137	11137	11137	11137	11137	11137	11137	11137	11137	11137	11137	11137	11137	11137	11137	11137	11137	11137	11137	11137	11137	11137	11137	11137	11137	11137	11137	11137	11137	11137	11137	11137	11137	11137	11137	11137	11137	11137	11137	11137	11137	11137	11137	11137	11137	11137	11137	11137	11137	11137	11137	11137	11137	11137	11137	11137	11137	11137	11137	11137	11137	11137	11137	11137	11137	11137	11137	11137	11137

base['round_winner'].value_counts()

T     62406
CT    60004
Name: round_winner, dtype: int64

base.describe().transpose()

	count	mean	std	min	25%	50%	75%	max
time_left	122410.0	97.886922	54.465238	0.01	54.92	94.91	166.9175	175.0
ct_score	122410.0	6.709239	4.790362	0.00	3.00	6.00	10.0000	32.0
t_score	122410.0	6.780435	4.823543	0.00	3.00	6.00	10.0000	33.0
ct_health	122410.0	412.106568	132.293290	0.00	350.00	500.00	500.0000	500.0
t_health	122410.0	402.714500	139.919033	0.00	322.00	500.00	500.0000	600.0
...	...	...	...	...	...	...	...	...
t_grenade_incendiarygrenade	122410.0	0.019819	0.143933	0.00	0.00	0.00	0.0000	3.0
ct_grenade_molotovgrenade	122410.0	0.048011	0.227669	0.00	0.00	0.00	0.0000	3.0
t_grenade_molotovgrenade	122410.0	1.352095	1.663246	0.00	0.00	1.00	2.0000	5.0
ct_grenade_decoygrenade	122410.0	0.027694	0.169531	0.00	0.00	0.00	0.0000	3.0
t_grenade_decoygrenade	122410.0	0.025750	0.164162	0.00	0.00	0.00	0.0000	2.0

92 rows × 8 columns

base.dtypes

time_left                    float64
ct_score                       int64
t_score                        int64
map                           object
ct_health                      int64
                              ...   
ct_grenade_molotovgrenade      int64
t_grenade_molotovgrenade       int64
ct_grenade_decoygrenade        int64
t_grenade_decoygrenade         int64
round_winner                  object
Length: 94, dtype: object

pd.set_option('display.max_columns', None)

base.head()

	time_left	ct_score	t_score	map	ct_health	t_health	ct_money	t_money	ct_helmets	t_helmets	ct_defuse_kits	ct_players_alive	t_players_alive	ct_weapon_ak47	t_weapon_ak47	ct_weapon_aug	t_weapon_aug	ct_weapon_awp	t_weapon_awp	ct_weapon_bizon	t_weapon_bizon	ct_weapon_cz75auto	t_weapon_cz75auto	ct_weapon_elite	t_weapon_elite	ct_weapon_famas	t_weapon_famas	ct_weapon_g3sg1	t_weapon_g3sg1	ct_weapon_galilar	t_weapon_galilar	ct_weapon_glock	t_weapon_glock	ct_weapon_m249	t_weapon_m249	ct_weapon_m4a1s	t_weapon_m4a1s	ct_weapon_m4a4	t_weapon_m4a4	ct_weapon_mac10	t_weapon_mac10	ct_weapon_mag7	t_weapon_mag7	ct_weapon_mp5sd	t_weapon_mp5sd	ct_weapon_mp7	t_weapon_mp7	ct_weapon_mp9	t_weapon_mp9	ct_weapon_negev	t_weapon_negev	ct_weapon_nova	t_weapon_nova	ct_weapon_p90	t_weapon_p90	ct_weapon_r8revolver	t_weapon_r8revolver	ct_weapon_sawedoff	t_weapon_sawedoff	ct_weapon_scar20	t_weapon_scar20	ct_weapon_sg553	t_weapon_sg553	ct_weapon_ssg08	t_weapon_ssg08	ct_weapon_ump45	t_weapon_ump45	ct_weapon_xm1014	t_weapon_xm1014	ct_weapon_deagle	t_weapon_deagle	ct_weapon_fiveseven	t_weapon_fiveseven	ct_weapon_usps	t_weapon_usps	ct_weapon_p250	t_weapon_p250	ct_weapon_p2000	t_weapon_p2000	ct_weapon_tec9	t_weapon_tec9	ct_grenade_hegrenade	t_grenade_hegrenade	ct_grenade_flashbang	t_grenade_flashbang	ct_grenade_smokegrenade	t_grenade_smokegrenade	ct_grenade_incendiarygrenade	t_grenade_incendiarygrenade	ct_grenade_molotovgrenade	t_grenade_molotovgrenade	ct_grenade_decoygrenade	t_grenade_decoygrenade	round_winner
0	175.00	0	0	de_dust2	500	500	4000	4000	0	0	0	5	5	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	5	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	4	0	0	0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	CT
1	156.03	0	0	de_dust2	500	500	600	650	0	0	1	5	5	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	5	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	4	0	0	0	1	0	0	0	0	0	0	0	0	2	0	0	0	0	0	0	CT
2	96.03	0	0	de_dust2	391	400	750	500	0	0	1	4	4	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	4	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	4	0	0	0	0	0	0	0	0	0	0	0	0	2	0	0	0	0	0	0	CT
3	76.03	0	0	de_dust2	391	400	750	500	0	0	1	4	4	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	3	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	4	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	CT
4	174.97	1	0	de_dust2	500	500	18350	10750	0	0	1	5	5	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	5	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	4	0	0	0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	CT

plt.figure(figsize=(20,5))

# Plot sepal width as a function of sepal_length across days
g = sns.lmplot(
    data=base,
    x="ct_score", y="t_score", hue="round_winner",
    height=5
)

# Use more informative axis labels than are provided by default
g.set_axis_labels("Score - Multiple linear regression ", "round_winner ")

<seaborn.axisgrid.FacetGrid at 0x28c6743dd30>

<Figure size 1440x360 with 0 Axes>

# Plot sepal width as a function of sepal_length across days
g = sns.lmplot(
    data=base,
    x="ct_health", y="t_health", hue="round_winner",
    height=5
)

# Use more informative axis labels than are provided by default
g.set_axis_labels("Health - Multiple linear regression ", "round_winner ")

<seaborn.axisgrid.FacetGrid at 0x28c64469d60>

plt.figure(figsize=(20,5))

sns.histplot(base[base['t_health']<=0.2 * 1e8 ]['ct_health'])

<AxesSubplot:xlabel='ct_health', ylabel='Count'>

Padronização de CT e T

Resolvi que para andar com o processo de analise exploratoria, preciso formatar os dados de string para tipos inteiros,usei um metodo de aplicação de apply para remover tudo que for string ct para 0 e T para 1, quero ver como é o comportamento do processo de t_score tambem, como ele se comporta em relação ao quantidade total por partida

base['round_winner'] = base['round_winner'].apply(lambda var: 0 if var == 'CT' else 1)

plt.figure(figsize=(20,5))

sns.histplot(base[base['t_score']<=0.2 * 1e8 ]['t_score'])

<AxesSubplot:xlabel='t_score', ylabel='Count'>

Automação Exploração de Dadaos (sweetviz)

!pip3 install sweetviz
!pip3 install ipywidgets

Looking in indexes: https://pypi.org/simple, http://nexus.viavarejo.com.br/repository/pypi-data-science/simple, http://nexus.viavarejo.com.br/repository/pypi-data-science/pypi

WARNING: Retrying (Retry(total=4, connect=None, read=None, redirect=None, status=None)) after connection broken by 'NewConnectionError('<pip._vendor.urllib3.connection.HTTPConnection object at 0x000002659C4D4280>: Failed to establish a new connection: [Errno 11001] getaddrinfo failed')': /repository/pypi-data-science/simple/sweetviz/
WARNING: Retrying (Retry(total=3, connect=None, read=None, redirect=None, status=None)) after connection broken by 'NewConnectionError('<pip._vendor.urllib3.connection.HTTPConnection object at 0x000002659C4D44F0>: Failed to establish a new connection: [Errno 11001] getaddrinfo failed')': /repository/pypi-data-science/simple/sweetviz/
WARNING: Retrying (Retry(total=2, connect=None, read=None, redirect=None, status=None)) after connection broken by 'NewConnectionError('<pip._vendor.urllib3.connection.HTTPConnection object at 0x000002659C4D4760>: Failed to establish a new connection: [Errno 11001] getaddrinfo failed')': /repository/pypi-data-science/simple/sweetviz/
WARNING: Retrying (Retry(total=1, connect=None, read=None, redirect=None, status=None)) after connection broken by 'NewConnectionError('<pip._vendor.urllib3.connection.HTTPConnection object at 0x000002659C4D49A0>: Failed to establish a new connection: [Errno 11001] getaddrinfo failed')': /repository/pypi-data-science/simple/sweetviz/
WARNING: Retrying (Retry(total=0, connect=None, read=None, redirect=None, status=None)) after connection broken by 'NewConnectionError('<pip._vendor.urllib3.connection.HTTPConnection object at 0x000002659C4D4BE0>: Failed to establish a new connection: [Errno 11001] getaddrinfo failed')': /repository/pypi-data-science/simple/sweetviz/
WARNING: Retrying (Retry(total=4, connect=None, read=None, redirect=None, status=None)) after connection broken by 'NewConnectionError('<pip._vendor.urllib3.connection.HTTPConnection object at 0x000002659C4D48B0>: Failed to establish a new connection: [Errno 11001] getaddrinfo failed')': /repository/pypi-data-science/pypi/sweetviz/
WARNING: Retrying (Retry(total=3, connect=None, read=None, redirect=None, status=None)) after connection broken by 'NewConnectionError('<pip._vendor.urllib3.connection.HTTPConnection object at 0x000002659C4D4D90>: Failed to establish a new connection: [Errno 11001] getaddrinfo failed')': /repository/pypi-data-science/pypi/sweetviz/
WARNING: Retrying (Retry(total=2, connect=None, read=None, redirect=None, status=None)) after connection broken by 'NewConnectionError('<pip._vendor.urllib3.connection.HTTPConnection object at 0x000002659C4D4970>: Failed to establish a new connection: [Errno 11001] getaddrinfo failed')': /repository/pypi-data-science/pypi/sweetviz/
WARNING: Retrying (Retry(total=1, connect=None, read=None, redirect=None, status=None)) after connection broken by 'NewConnectionError('<pip._vendor.urllib3.connection.HTTPConnection object at 0x000002659C4D44F0>: Failed to establish a new connection: [Errno 11001] getaddrinfo failed')': /repository/pypi-data-science/pypi/sweetviz/
WARNING: Retrying (Retry(total=0, connect=None, read=None, redirect=None, status=None)) after connection broken by 'NewConnectionError('<pip._vendor.urllib3.connection.HTTPConnection object at 0x000002659C4D4370>: Failed to establish a new connection: [Errno 11001] getaddrinfo failed')': /repository/pypi-data-science/pypi/sweetviz/
WARNING: Retrying (Retry(total=4, connect=None, read=None, redirect=None, status=None)) after connection broken by 'NewConnectionError('<pip._vendor.urllib3.connection.HTTPConnection object at 0x000002659C53C490>: Failed to establish a new connection: [Errno 11001] getaddrinfo failed')': /repository/pypi-data-science/simple/importlib-resources/
WARNING: Retrying (Retry(total=3, connect=None, read=None, redirect=None, status=None)) after connection broken by 'NewConnectionError('<pip._vendor.urllib3.connection.HTTPConnection object at 0x000002659C53C6A0>: Failed to establish a new connection: [Errno 11001] getaddrinfo failed')': /repository/pypi-data-science/simple/importlib-resources/
WARNING: Retrying (Retry(total=2, connect=None, read=None, redirect=None, status=None)) after connection broken by 'NewConnectionError('<pip._vendor.urllib3.connection.HTTPConnection object at 0x000002659C53C8E0>: Failed to establish a new connection: [Errno 11001] getaddrinfo failed')': /repository/pypi-data-science/simple/importlib-resources/
WARNING: Retrying (Retry(total=1, connect=None, read=None, redirect=None, status=None)) after connection broken by 'NewConnectionError('<pip._vendor.urllib3.connection.HTTPConnection object at 0x000002659C53CB20>: Failed to establish a new connection: [Errno 11001] getaddrinfo failed')': /repository/pypi-data-science/simple/importlib-resources/
WARNING: Retrying (Retry(total=0, connect=None, read=None, redirect=None, status=None)) after connection broken by 'NewConnectionError('<pip._vendor.urllib3.connection.HTTPConnection object at 0x000002659C53CD60>: Failed to establish a new connection: [Errno 11001] getaddrinfo failed')': /repository/pypi-data-science/simple/importlib-resources/
WARNING: Retrying (Retry(total=4, connect=None, read=None, redirect=None, status=None)) after connection broken by 'NewConnectionError('<pip._vendor.urllib3.connection.HTTPConnection object at 0x000002659C548310>: Failed to establish a new connection: [Errno 11001] getaddrinfo failed')': /repository/pypi-data-science/pypi/importlib-resources/
WARNING: Retrying (Retry(total=3, connect=None, read=None, redirect=None, status=None)) after connection broken by 'NewConnectionError('<pip._vendor.urllib3.connection.HTTPConnection object at 0x000002659C548520>: Failed to establish a new connection: [Errno 11001] getaddrinfo failed')': /repository/pypi-data-science/pypi/importlib-resources/
WARNING: Retrying (Retry(total=2, connect=None, read=None, redirect=None, status=None)) after connection broken by 'NewConnectionError('<pip._vendor.urllib3.connection.HTTPConnection object at 0x000002659C548790>: Failed to establish a new connection: [Errno 11001] getaddrinfo failed')': /repository/pypi-data-science/pypi/importlib-resources/
WARNING: Retrying (Retry(total=1, connect=None, read=None, redirect=None, status=None)) after connection broken by 'NewConnectionError('<pip._vendor.urllib3.connection.HTTPConnection object at 0x000002659C5489D0>: Failed to establish a new connection: [Errno 11001] getaddrinfo failed')': /repository/pypi-data-science/pypi/importlib-resources/
WARNING: Retrying (Retry(total=0, connect=None, read=None, redirect=None, status=None)) after connection broken by 'NewConnectionError('<pip._vendor.urllib3.connection.HTTPConnection object at 0x000002659C548C10>: Failed to establish a new connection: [Errno 11001] getaddrinfo failed')': /repository/pypi-data-science/pypi/importlib-resources/
WARNING: You are using pip version 21.0.1; however, version 21.3.1 is available.
You should consider upgrading via the 'c:\users\2104944461\anaconda3\python.exe -m pip install --upgrade pip' command.

Collecting sweetviz
  Downloading sweetviz-2.1.3-py3-none-any.whl (15.1 MB)
Requirement already satisfied: pandas!=1.0.0,!=1.0.1,!=1.0.2,>=0.25.3 in c:\users\2104944461\anaconda3\lib\site-packages (from sweetviz) (1.1.3)
Requirement already satisfied: jinja2>=2.11.1 in c:\users\2104944461\anaconda3\lib\site-packages (from sweetviz) (2.11.2)
Requirement already satisfied: tqdm>=4.43.0 in c:\users\2104944461\anaconda3\lib\site-packages (from sweetviz) (4.50.2)
Collecting importlib-resources>=1.2.0
  Downloading importlib_resources-5.4.0-py3-none-any.whl (28 kB)
Requirement already satisfied: scipy>=1.3.2 in c:\users\2104944461\anaconda3\lib\site-packages (from sweetviz) (1.6.1)
Requirement already satisfied: matplotlib>=3.1.3 in c:\users\2104944461\anaconda3\lib\site-packages (from sweetviz) (3.3.2)
Requirement already satisfied: numpy>=1.16.0 in c:\users\2104944461\anaconda3\lib\site-packages (from sweetviz) (1.19.5)
Requirement already satisfied: zipp>=3.1.0 in c:\users\2104944461\anaconda3\lib\site-packages (from importlib-resources>=1.2.0->sweetviz) (3.4.0)
Requirement already satisfied: MarkupSafe>=0.23 in c:\users\2104944461\anaconda3\lib\site-packages (from jinja2>=2.11.1->sweetviz) (1.1.1)
Requirement already satisfied: pillow>=6.2.0 in c:\users\2104944461\anaconda3\lib\site-packages (from matplotlib>=3.1.3->sweetviz) (8.0.1)
Requirement already satisfied: cycler>=0.10 in c:\users\2104944461\anaconda3\lib\site-packages (from matplotlib>=3.1.3->sweetviz) (0.10.0)
Requirement already satisfied: kiwisolver>=1.0.1 in c:\users\2104944461\anaconda3\lib\site-packages (from matplotlib>=3.1.3->sweetviz) (1.3.0)
Requirement already satisfied: pyparsing!=2.0.4,!=2.1.2,!=2.1.6,>=2.0.3 in c:\users\2104944461\anaconda3\lib\site-packages (from matplotlib>=3.1.3->sweetviz) (2.4.7)
Requirement already satisfied: python-dateutil>=2.1 in c:\users\2104944461\anaconda3\lib\site-packages (from matplotlib>=3.1.3->sweetviz) (2.8.1)
Requirement already satisfied: certifi>=2020.06.20 in c:\users\2104944461\anaconda3\lib\site-packages (from matplotlib>=3.1.3->sweetviz) (2020.12.5)
Requirement already satisfied: six in c:\users\2104944461\anaconda3\lib\site-packages (from cycler>=0.10->matplotlib>=3.1.3->sweetviz) (1.15.0)
Requirement already satisfied: pytz>=2017.2 in c:\users\2104944461\anaconda3\lib\site-packages (from pandas!=1.0.0,!=1.0.1,!=1.0.2,>=0.25.3->sweetviz) (2020.1)
Installing collected packages: importlib-resources, sweetviz
Successfully installed importlib-resources-5.4.0 sweetviz-2.1.3

WARNING: You are using pip version 21.0.1; however, version 21.3.1 is available.
You should consider upgrading via the 'c:\users\2104944461\anaconda3\python.exe -m pip install --upgrade pip' command.

Looking in indexes: https://pypi.org/simple, http://nexus.viavarejo.com.br/repository/pypi-data-science/simple, http://nexus.viavarejo.com.br/repository/pypi-data-science/pypi
Requirement already satisfied: ipywidgets in c:\users\2104944461\anaconda3\lib\site-packages (7.5.1)
Requirement already satisfied: nbformat>=4.2.0 in c:\users\2104944461\appdata\roaming\python\python38\site-packages (from ipywidgets) (5.1.3)
Requirement already satisfied: traitlets>=4.3.1 in c:\users\2104944461\anaconda3\lib\site-packages (from ipywidgets) (5.0.5)
Requirement already satisfied: ipykernel>=4.5.1 in c:\users\2104944461\anaconda3\lib\site-packages (from ipywidgets) (5.3.4)
Requirement already satisfied: widgetsnbextension~=3.5.0 in c:\users\2104944461\anaconda3\lib\site-packages (from ipywidgets) (3.5.1)
Requirement already satisfied: ipython>=4.0.0 in c:\users\2104944461\anaconda3\lib\site-packages (from ipywidgets) (7.19.0)
Requirement already satisfied: tornado>=4.2 in c:\users\2104944461\anaconda3\lib\site-packages (from ipykernel>=4.5.1->ipywidgets) (6.0.4)
Requirement already satisfied: jupyter-client in c:\users\2104944461\anaconda3\lib\site-packages (from ipykernel>=4.5.1->ipywidgets) (6.1.7)
Requirement already satisfied: colorama in c:\users\2104944461\anaconda3\lib\site-packages (from ipython>=4.0.0->ipywidgets) (0.4.4)
Requirement already satisfied: decorator in c:\users\2104944461\anaconda3\lib\site-packages (from ipython>=4.0.0->ipywidgets) (4.4.2)
Requirement already satisfied: jedi>=0.10 in c:\users\2104944461\anaconda3\lib\site-packages (from ipython>=4.0.0->ipywidgets) (0.17.1)
Requirement already satisfied: pygments in c:\users\2104944461\anaconda3\lib\site-packages (from ipython>=4.0.0->ipywidgets) (2.7.2)
Requirement already satisfied: backcall in c:\users\2104944461\anaconda3\lib\site-packages (from ipython>=4.0.0->ipywidgets) (0.2.0)
Requirement already satisfied: pickleshare in c:\users\2104944461\anaconda3\lib\site-packages (from ipython>=4.0.0->ipywidgets) (0.7.5)
Requirement already satisfied: prompt-toolkit!=3.0.0,!=3.0.1,<3.1.0,>=2.0.0 in c:\users\2104944461\anaconda3\lib\site-packages (from ipython>=4.0.0->ipywidgets) (3.0.8)
Requirement already satisfied: setuptools>=18.5 in c:\users\2104944461\anaconda3\lib\site-packages (from ipython>=4.0.0->ipywidgets) (50.3.1.post20201107)
Requirement already satisfied: parso<0.8.0,>=0.7.0 in c:\users\2104944461\anaconda3\lib\site-packages (from jedi>=0.10->ipython>=4.0.0->ipywidgets) (0.7.0)
Requirement already satisfied: ipython-genutils in c:\users\2104944461\anaconda3\lib\site-packages (from nbformat>=4.2.0->ipywidgets) (0.2.0)
Requirement already satisfied: jupyter-core in c:\users\2104944461\anaconda3\lib\site-packages (from nbformat>=4.2.0->ipywidgets) (4.6.3)
Requirement already satisfied: jsonschema!=2.5.0,>=2.4 in c:\users\2104944461\anaconda3\lib\site-packages (from nbformat>=4.2.0->ipywidgets) (3.2.0)
Requirement already satisfied: attrs>=17.4.0 in c:\users\2104944461\anaconda3\lib\site-packages (from jsonschema!=2.5.0,>=2.4->nbformat>=4.2.0->ipywidgets) (20.3.0)
Requirement already satisfied: pyrsistent>=0.14.0 in c:\users\2104944461\anaconda3\lib\site-packages (from jsonschema!=2.5.0,>=2.4->nbformat>=4.2.0->ipywidgets) (0.17.3)
Requirement already satisfied: six>=1.11.0 in c:\users\2104944461\anaconda3\lib\site-packages (from jsonschema!=2.5.0,>=2.4->nbformat>=4.2.0->ipywidgets) (1.15.0)
Requirement already satisfied: wcwidth in c:\users\2104944461\anaconda3\lib\site-packages (from prompt-toolkit!=3.0.0,!=3.0.1,<3.1.0,>=2.0.0->ipython>=4.0.0->ipywidgets) (0.2.5)
Requirement already satisfied: notebook>=4.4.1 in c:\users\2104944461\anaconda3\lib\site-packages (from widgetsnbextension~=3.5.0->ipywidgets) (6.1.4)
Requirement already satisfied: argon2-cffi in c:\users\2104944461\anaconda3\lib\site-packages (from notebook>=4.4.1->widgetsnbextension~=3.5.0->ipywidgets) (20.1.0)
Requirement already satisfied: terminado>=0.8.3 in c:\users\2104944461\anaconda3\lib\site-packages (from notebook>=4.4.1->widgetsnbextension~=3.5.0->ipywidgets) (0.9.1)
Requirement already satisfied: pyzmq>=17 in c:\users\2104944461\anaconda3\lib\site-packages (from notebook>=4.4.1->widgetsnbextension~=3.5.0->ipywidgets) (19.0.2)
Requirement already satisfied: prometheus-client in c:\users\2104944461\anaconda3\lib\site-packages (from notebook>=4.4.1->widgetsnbextension~=3.5.0->ipywidgets) (0.8.0)
Requirement already satisfied: Send2Trash in c:\users\2104944461\anaconda3\lib\site-packages (from notebook>=4.4.1->widgetsnbextension~=3.5.0->ipywidgets) (1.5.0)
Requirement already satisfied: nbconvert in c:\users\2104944461\anaconda3\lib\site-packages (from notebook>=4.4.1->widgetsnbextension~=3.5.0->ipywidgets) (6.0.7)
Requirement already satisfied: jinja2 in c:\users\2104944461\anaconda3\lib\site-packages (from notebook>=4.4.1->widgetsnbextension~=3.5.0->ipywidgets) (2.11.2)
Requirement already satisfied: python-dateutil>=2.1 in c:\users\2104944461\anaconda3\lib\site-packages (from jupyter-client->ipykernel>=4.5.1->ipywidgets) (2.8.1)
Requirement already satisfied: pywin32>=1.0 in c:\users\2104944461\anaconda3\lib\site-packages (from jupyter-core->nbformat>=4.2.0->ipywidgets) (227)
Requirement already satisfied: pywinpty>=0.5 in c:\users\2104944461\anaconda3\lib\site-packages (from terminado>=0.8.3->notebook>=4.4.1->widgetsnbextension~=3.5.0->ipywidgets) (0.5.7)
Requirement already satisfied: cffi>=1.0.0 in c:\users\2104944461\anaconda3\lib\site-packages (from argon2-cffi->notebook>=4.4.1->widgetsnbextension~=3.5.0->ipywidgets) (1.14.3)
Requirement already satisfied: pycparser in c:\users\2104944461\anaconda3\lib\site-packages (from cffi>=1.0.0->argon2-cffi->notebook>=4.4.1->widgetsnbextension~=3.5.0->ipywidgets) (2.20)
Requirement already satisfied: MarkupSafe>=0.23 in c:\users\2104944461\anaconda3\lib\site-packages (from jinja2->notebook>=4.4.1->widgetsnbextension~=3.5.0->ipywidgets) (1.1.1)
Requirement already satisfied: defusedxml in c:\users\2104944461\anaconda3\lib\site-packages (from nbconvert->notebook>=4.4.1->widgetsnbextension~=3.5.0->ipywidgets) (0.6.0)
Requirement already satisfied: entrypoints>=0.2.2 in c:\users\2104944461\anaconda3\lib\site-packages (from nbconvert->notebook>=4.4.1->widgetsnbextension~=3.5.0->ipywidgets) (0.3)
Requirement already satisfied: testpath in c:\users\2104944461\anaconda3\lib\site-packages (from nbconvert->notebook>=4.4.1->widgetsnbextension~=3.5.0->ipywidgets) (0.4.4)
Requirement already satisfied: mistune<2,>=0.8.1 in c:\users\2104944461\anaconda3\lib\site-packages (from nbconvert->notebook>=4.4.1->widgetsnbextension~=3.5.0->ipywidgets) (0.8.4)
Requirement already satisfied: nbclient<0.6.0,>=0.5.0 in c:\users\2104944461\anaconda3\lib\site-packages (from nbconvert->notebook>=4.4.1->widgetsnbextension~=3.5.0->ipywidgets) (0.5.1)
Requirement already satisfied: jupyterlab-pygments in c:\users\2104944461\anaconda3\lib\site-packages (from nbconvert->notebook>=4.4.1->widgetsnbextension~=3.5.0->ipywidgets) (0.1.2)
Requirement already satisfied: bleach in c:\users\2104944461\anaconda3\lib\site-packages (from nbconvert->notebook>=4.4.1->widgetsnbextension~=3.5.0->ipywidgets) (3.2.1)
Requirement already satisfied: pandocfilters>=1.4.1 in c:\users\2104944461\anaconda3\lib\site-packages (from nbconvert->notebook>=4.4.1->widgetsnbextension~=3.5.0->ipywidgets) (1.4.3)
Requirement already satisfied: async-generator in c:\users\2104944461\anaconda3\lib\site-packages (from nbclient<0.6.0,>=0.5.0->nbconvert->notebook>=4.4.1->widgetsnbextension~=3.5.0->ipywidgets) (1.10)
Requirement already satisfied: nest-asyncio in c:\users\2104944461\anaconda3\lib\site-packages (from nbclient<0.6.0,>=0.5.0->nbconvert->notebook>=4.4.1->widgetsnbextension~=3.5.0->ipywidgets) (1.4.2)
Requirement already satisfied: webencodings in c:\users\2104944461\anaconda3\lib\site-packages (from bleach->nbconvert->notebook>=4.4.1->widgetsnbextension~=3.5.0->ipywidgets) (0.5.1)
Requirement already satisfied: packaging in c:\users\2104944461\anaconda3\lib\site-packages (from bleach->nbconvert->notebook>=4.4.1->widgetsnbextension~=3.5.0->ipywidgets) (20.4)
Requirement already satisfied: pyparsing>=2.0.2 in c:\users\2104944461\anaconda3\lib\site-packages (from packaging->bleach->nbconvert->notebook>=4.4.1->widgetsnbextension~=3.5.0->ipywidgets) (2.4.7)

Percepções

PS: Percebi que usando sweetviz poderia automatizar o processo de EDA, poderia ter uma visualização mais completa olhando para todos os pontos que tive no começo, acredito que dessa forma, pouco tempo no processo de descobertas, com essa tecnica consigo entrar mais no detalhe e ter a percepção que o padrão das partidas variam de acordo com time e em relação a vida,dinheiro, tipo de arma, e classificação de ct ou t.

# por favor rode o sweetviz e veja o resultado da analise
try:
  import sweetviz as sv
  my_report = sv.analyze(base)
except: 
  print("Falha ao Instalar o Sweetviz")

Observação sobre ct_defuse_kit

Percebi que o grafico de barras apresenta uma distribuição em barras com os seguintes dados

TOP	CATEGORIES
042	09534%
127	40022%
217	21814%
315	38613%
412	01310%
58	2987%

try: 
  my_report.show_notebook()
except:
  print("Falha ao Gerar Relatorio no Notebook")

Mapeamento coluna Map

Para prosseguir com a base preciso mapear e converter a coluna map para um tipo string para isso mapei os index usando groubpy e em seguida usei a funcção do apply para fazer as trocas.

base[['map','round_winner']].groupby(['map']).count().T

map	de_cache	de_dust2	de_inferno	de_mirage	de_nuke	de_overpass	de_train	de_vertigo
round_winner	145	22144	23811	18576	19025	14081	13491	11137

maps = list(base[['map','round_winner']].groupby(['map']).count().T.to_dict().keys())

for dados in enumerate(maps):
     print(dados)

(0, 'de_cache')
(1, 'de_dust2')
(2, 'de_inferno')
(3, 'de_mirage')
(4, 'de_nuke')
(5, 'de_overpass')
(6, 'de_train')
(7, 'de_vertigo')

maps.index('de_vertigo')

7

base['map'] = base['map'].apply(lambda x:maps.index(x))

base['map'] 

0         1
1         1
2         1
3         1
4         1
         ..
122405    6
122406    6
122407    6
122408    6
122409    6
Name: map, Length: 122410, dtype: int64

base

	time_left	ct_score	t_score	map	ct_health	t_health	ct_money	t_money	ct_helmets	t_helmets	ct_defuse_kits	ct_players_alive	t_players_alive	ct_weapon_ak47	t_weapon_ak47	ct_weapon_aug	t_weapon_aug	ct_weapon_awp	t_weapon_awp	ct_weapon_bizon	t_weapon_bizon	ct_weapon_cz75auto	t_weapon_cz75auto	ct_weapon_elite	t_weapon_elite	ct_weapon_famas	t_weapon_famas	ct_weapon_g3sg1	t_weapon_g3sg1	ct_weapon_galilar	t_weapon_galilar	ct_weapon_glock	t_weapon_glock	ct_weapon_m249	t_weapon_m249	ct_weapon_m4a1s	t_weapon_m4a1s	ct_weapon_m4a4	t_weapon_m4a4	ct_weapon_mac10	t_weapon_mac10	ct_weapon_mag7	t_weapon_mag7	ct_weapon_mp5sd	t_weapon_mp5sd	ct_weapon_mp7	t_weapon_mp7	ct_weapon_mp9	t_weapon_mp9	ct_weapon_negev	t_weapon_negev	ct_weapon_nova	t_weapon_nova	ct_weapon_p90	t_weapon_p90	ct_weapon_r8revolver	t_weapon_r8revolver	ct_weapon_sawedoff	t_weapon_sawedoff	ct_weapon_scar20	t_weapon_scar20	ct_weapon_sg553	t_weapon_sg553	ct_weapon_ssg08	t_weapon_ssg08	ct_weapon_ump45	t_weapon_ump45	ct_weapon_xm1014	t_weapon_xm1014	ct_weapon_deagle	t_weapon_deagle	ct_weapon_fiveseven	t_weapon_fiveseven	ct_weapon_usps	t_weapon_usps	ct_weapon_p250	t_weapon_p250	ct_weapon_p2000	t_weapon_p2000	ct_weapon_tec9	t_weapon_tec9	ct_grenade_hegrenade	t_grenade_hegrenade	ct_grenade_flashbang	t_grenade_flashbang	ct_grenade_smokegrenade	t_grenade_smokegrenade	ct_grenade_incendiarygrenade	t_grenade_incendiarygrenade	ct_grenade_molotovgrenade	t_grenade_molotovgrenade	ct_grenade_decoygrenade	t_grenade_decoygrenade	round_winner
0	175.00	0	0	1	500	500	4000	4000	0	0	0	5	5	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	5	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	4	0	0	0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0
1	156.03	0	0	1	500	500	600	650	0	0	1	5	5	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	5	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	4	0	0	0	1	0	0	0	0	0	0	0	0	2	0	0	0	0	0	0	0
2	96.03	0	0	1	391	400	750	500	0	0	1	4	4	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	4	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	4	0	0	0	0	0	0	0	0	0	0	0	0	2	0	0	0	0	0	0	0
3	76.03	0	0	1	391	400	750	500	0	0	1	4	4	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	3	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	4	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0
4	174.97	1	0	1	500	500	18350	10750	0	0	1	5	5	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	5	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	4	0	0	0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
122405	15.41	11	14	6	200	242	100	5950	2	4	1	2	4	0	1	0	0	0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2	0	0	0	0	1	0	0	0	0	0	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	2	0	0	0	0	0	0	0	0	0	0	2	0	0	2	0	0	0	0	0	0	1	2	1	1	0	0	0	0	0	0	1
122406	174.93	11	15	6	500	500	11500	23900	1	2	1	5	5	0	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	5	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	5	0	0	0	0	0	0	0	0	0	1	2	1	0	0	0	0	0	0	0	1
122407	114.93	11	15	6	500	500	1200	6700	3	5	1	5	5	0	2	0	0	0	1	0	0	1	0	0	0	0	0	0	0	0	0	0	4	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0	0	0	0	0	0	3	1	0	0	1	0	0	0	0	0	0	0	2	0	4	4	3	5	1	0	0	5	0	0	1
122408	94.93	11	15	6	500	500	1200	6700	3	5	1	5	5	0	2	0	0	0	1	0	0	1	0	0	0	0	0	0	0	0	0	0	4	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	2	0	0	0	0	0	0	3	1	0	0	1	0	0	0	0	0	0	0	2	0	1	5	0	3	0	0	0	4	0	0	1
122409	74.93	11	15	6	375	479	1100	7000	2	5	1	4	5	0	2	0	0	0	1	0	0	1	0	0	0	0	0	0	0	0	0	0	4	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	2	0	0	0	0	0	0	2	1	0	0	1	0	0	0	0	0	0	0	0	0	0	3	0	2	0	0	0	3	0	0	1

122410 rows × 94 columns

base['ct_score']

0          0
1          0
2          0
3          0
4          1
          ..
122405    11
122406    11
122407    11
122408    11
122409    11
Name: ct_score, Length: 122398, dtype: int64

def detect_outlier(data):
    # find q1 and q3 values
    q1, q3 = np.percentile(sorted(data), [25, 75])
 
    # compute IRQ
    iqr = q3 - q1
 
    # find lower and upper bounds
    lower_bound = q1 - (1.5 * iqr)
    upper_bound = q3 + (1.5 * iqr)
 
    outliers = [x for x in data if x <= lower_bound or x >= upper_bound]
 
    return outliers

base.drop(detect_outlier(base['ct_score']),inplace=True)

base.describe().T

	count	mean	std	min	25%	50%	75%	max
time_left	122398.0	97.885604	54.465466	0.01	54.92	94.91	166.91	175.0
ct_score	122398.0	6.709603	4.790456	0.00	3.00	6.00	10.00	32.0
t_score	122398.0	6.780952	4.823494	0.00	3.00	6.00	10.00	33.0
map	122398.0	3.520417	1.929022	0.00	2.00	3.00	5.00	7.0
ct_health	122398.0	412.111840	132.289775	0.00	350.00	500.00	500.00	500.0
...	...	...	...	...	...	...	...	...
ct_grenade_molotovgrenade	122398.0	0.048015	0.227680	0.00	0.00	0.00	0.00	3.0
t_grenade_molotovgrenade	122398.0	1.352016	1.663186	0.00	0.00	1.00	2.00	5.0
ct_grenade_decoygrenade	122398.0	0.027697	0.169539	0.00	0.00	0.00	0.00	3.0
t_grenade_decoygrenade	122398.0	0.025752	0.164170	0.00	0.00	0.00	0.00	2.0
round_winner	122398.0	0.509771	0.499907	0.00	0.00	1.00	1.00	1.0

94 rows × 8 columns

Gerando Base para Treino

base.to_csv("treino_08_31_00_31-10-2021.csv",index=False)